{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2CZ7Q2ZXT6S7OXKBOOJBOZINMB","short_pith_number":"pith:2CZ7Q2ZX","schema_version":"1.0","canonical_sha256":"d0b3f86b379fa5f75d41739217650d606098344d095d19ace5509b6f07cb80b6","source":{"kind":"arxiv","id":"2503.08308","version":1},"attestation_state":"computed","paper":{"title":"Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Daneshmend, Andreas Demosthenous, Chen Feng, Da Li, Lu Yin, Miguel R. D. Rodrigues, Mine Orlu, Zhuo Zhi, Ziquan Liu","submitted_at":"2025-03-11T11:18:53Z","abstract_excerpt":"Multimodal large language models (MLLMs) show promise in tasks like visual question answering (VQA) but still face challenges in multimodal reasoning. Recent works adapt agentic frameworks or chain-of-thought (CoT) reasoning to improve performance. However, CoT-based multimodal reasoning often demands costly data annotation and fine-tuning, while agentic approaches relying on external tools risk introducing unreliable output from these tools. In this paper, we propose Seeing and Reasoning with Confidence (SRICE), a training-free multimodal reasoning framework that integrates external vision mo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.08308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-11T11:18:53Z","cross_cats_sorted":[],"title_canon_sha256":"6f37fb5d54c10a7c874f920da5b643d1ed730aa72ff6817b5948b1db9a6ffff1","abstract_canon_sha256":"f237d597ff3da18cff5ea4f3102ca085f347c99e0c97b18851f77cc86bc57478"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:56.319321Z","signature_b64":"qpwvTXwLPrs7qvN7nBjH2N85PPyyPJp+Rxq3Bvvk1zHOwYgcBtlwWTXkBd7Rh6m8Cj/rDS9ErYWYsJ4Kyh8/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0b3f86b379fa5f75d41739217650d606098344d095d19ace5509b6f07cb80b6","last_reissued_at":"2026-07-05T10:28:56.318800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:56.318800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Daneshmend, Andreas Demosthenous, Chen Feng, Da Li, Lu Yin, Miguel R. D. Rodrigues, Mine Orlu, Zhuo Zhi, Ziquan Liu","submitted_at":"2025-03-11T11:18:53Z","abstract_excerpt":"Multimodal large language models (MLLMs) show promise in tasks like visual question answering (VQA) but still face challenges in multimodal reasoning. Recent works adapt agentic frameworks or chain-of-thought (CoT) reasoning to improve performance. However, CoT-based multimodal reasoning often demands costly data annotation and fine-tuning, while agentic approaches relying on external tools risk introducing unreliable output from these tools. In this paper, we propose Seeing and Reasoning with Confidence (SRICE), a training-free multimodal reasoning framework that integrates external vision mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08308","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.08308/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.08308","created_at":"2026-07-05T10:28:56.318865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08308v1","created_at":"2026-07-05T10:28:56.318865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08308","created_at":"2026-07-05T10:28:56.318865+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CZ7Q2ZXT6S7","created_at":"2026-07-05T10:28:56.318865+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CZ7Q2ZXT6S7OXKB","created_at":"2026-07-05T10:28:56.318865+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CZ7Q2ZX","created_at":"2026-07-05T10:28:56.318865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12623","citing_title":"Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB","json":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB.json","graph_json":"https://pith.science/api/pith-number/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/graph.json","events_json":"https://pith.science/api/pith-number/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/events.json","paper":"https://pith.science/paper/2CZ7Q2ZX"},"agent_actions":{"view_html":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB","download_json":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB.json","view_paper":"https://pith.science/paper/2CZ7Q2ZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08308&json=true","fetch_graph":"https://pith.science/api/pith-number/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/graph.json","fetch_events":"https://pith.science/api/pith-number/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/action/storage_attestation","attest_author":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/action/author_attestation","sign_citation":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/action/citation_signature","submit_replication":"https://pith.science/pith/2CZ7Q2ZXT6S7OXKBOOJBOZINMB/action/replication_record"}},"created_at":"2026-07-05T10:28:56.318865+00:00","updated_at":"2026-07-05T10:28:56.318865+00:00"}